Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4986 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3110. Min Range: -1.3110

Max Act: 1.3110. Min Act: 0.0000

Data Index: 173314 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.9490. Min Act: 0.0000

Data Index: 395460 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1371691 (Python Code)

Max Activating Token Index: 676

Text #3

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1140970 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.8973. Min Act: 0.0000

Data Index: 844345 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.9555. Min Act: 0.0000

Data Index: 559372 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.8481. Min Act: -0.0000

Data Index: 988216 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.8532. Min Act: -0.0000

Data Index: 169970 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.8479. Min Act: 0.0000

Data Index: 1005153 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.8440. Min Act: -0.0000

Data Index: 389956 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.8416. Min Act: -0.0000

Data Index: 532070 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.8234. Min Act: -0.0000

Data Index: 960415 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.7758. Min Act: 0.0000

Data Index: 478256 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1065034 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.7528. Min Act: -0.0000

Data Index: 750507 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.7259. Min Act: -0.0000

Data Index: 999069 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.7416. Min Act: -0.0000

Data Index: 293724 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.7137. Min Act: -0.0000

Data Index: 442330 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.6878. Min Act: 0.0000

Data Index: 1199501 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.3110. Min Range: -1.3110

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1451611 (Python Code)

Max Activating Token Index: 169